Model comparison
Muse Spark vs Step 2 16k Exp 202412
Muse Spark is the stronger model overall, scoring 50.6 to 39.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Muse Spark scores higher in 8 categories and Step 2 16k Exp 202412 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 35.2.
Side by side
| Muse Spark | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 50.6 | 39.2 |
| Released | 2026-04-08 | — |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 27 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Muse Spark: 46.2 (#69), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Muse Spark | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1481 | 1316 |
| SciCode | 51.5% | — |
Reasoning Muse Spark leads
Muse Spark: 35.9 (#67), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Muse Spark | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1474 | 1299 |
| CritPt | 11.3% | — |
| Epoch Capabilities Index | 152.04 | — |
Math Muse Spark leads
Muse Spark: 47.8 (#66), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Muse Spark | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1455 | 1304 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 17% | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Muse Spark leads
Muse Spark: 65.7 (#13), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Muse Spark | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1457 | 1279 |
| GPQA Diamond | 89.8% | — |
| Humanity's Last Exam | 40.6% | — |
Multimodal Not comparable
Muse Spark: 43.4 (#24), Step 2 16k Exp 202412: —
| Benchmark | Muse Spark | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Vision | 1306 | — |
| LMArena Document | 1444 | — |
Multilingual Muse Spark leads
Muse Spark: 56.1 (#24), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Muse Spark | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1464 | 1290 |
| LMArena Chinese | 1509 | 1331 |
| LMArena Russian | 1466 | 1324 |
| LMArena French | 1497 | — |
| LMArena German | 1497 | — |
| LMArena Korean | 1459 | — |
| LMArena Spanish | 1472 | — |
Instruction Following Muse Spark leads
Muse Spark: 75.9 (#51), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Muse Spark | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1442 | 1287 |
Long Context Muse Spark leads
Muse Spark: 44.4 (#69), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Muse Spark | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1451 | 1307 |
Writing & Preference Muse Spark leads
Muse Spark: 66.0 (#39), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Muse Spark | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1474 | 1321 |
| LMArena Creative Writing | 1459 | 1328 |
| LMArena Multi-Turn | 1477 | 1292 |
Frequently asked questions
Is Muse Spark better than Step 2 16k Exp 202412?
Muse Spark is the stronger model overall, scoring 50.6 to 39.2 on the Noometry Index.
Is Muse Spark or Step 2 16k Exp 202412 better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 38.5 in the Noometry coding category.
How many benchmarks do Muse Spark and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and Step 2 16k Exp 202412 has 12.